© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25760
    Prev
    Next
    INDEX
    Explanations

    obtained, converted, restore, learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶļ
    -0.07
    ãĤ¢ãĤ¦ãĥĪ
    -0.07
    atron
    -0.07
    ulsive
    -0.07
    éĥģ
    -0.06
    jak
    -0.06
    estellt
    -0.06
    iat
    -0.06
     guna
    -0.06
    æĪ¶
    -0.06
    POSITIVE LOGITS
    à¹Ĥà¸Ķยà¸ģาร
    0.12
    éĢļè¿ĩå°Ĩ
    0.11
    à¸Ķà¹īวยà¸ģาร
    0.11
    éĢļè¿ĩåľ¨
    0.11
     via
    0.10
     indem
    0.10
     пÑĥÑĤем
    0.10
     poprzez
    0.09
     mediante
    0.09
     à¸Ķà¹īวยà¸ģาร
    0.08
    Activations Density 0.352%

    No Known Activations